Slide 3
Slide 3 text
© GO Inc. 3
Segment Anything
Alexander Kirillov et al., arXiv, Apr 2023.
Recognize Anything: A Strong Image Tagging Model
Youcai Zhang et al., arXiv, Jun 2023.
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Lihe Yang et al., arXiv, Jan 2024.
The All-Seeing Project: Towards Panoptic Visual Recognition and
Understanding of the Open World
Weiyun Wang et al., ICLR, May 2024 (appeared on arXiv in Aug 2023).
紹介する論文
上記 4 本の X Anything 論文について、主にデータセット構築にフォーカスして紹介